5 datasets found

The Pascal Sentence dataset is a collection of images with 5 corresponding sentences as exact descriptions.

Wikipedia articles dataset is a dataset of image-text pairs designed for cross-modal retrieval applications.

The dataset used in the paper is the Wikipedia dataset, which contains over six million English Wikipedia articles with a full-text field associated with 50 training queries...

The ALADIN dataset is a custom dataset created for the ALADIN paper.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...